audit-a11y

/audit-a11y

Single-backend skill. Calls audit_a11y on the rolepod-uiproof MCP server. No fallback (D-024).

When to use

• Reviewing a UI for accessibility compliance before merging.
• After a UI change that touches markup, ARIA, or interactive components.
• During a periodic accessibility regression sweep.

When NOT to use

• Backend-only diffs.
• Pages that fail to render (server 500, blank page) — fix the page first.
• Auditing a single component when the rest of the page is not under test; scope-to-ref is v0.3 (currently scope='page' only).

Inputs

• target — URL to audit.
• level — wcag-a | wcag-aa | wcag-aaa. Default wcag-aa.
• report_format — json | markdown. Default json.

Outputs

• run_id — folder under ./.rolepod-uiproof/artifacts/.
• counts — issue counts by severity.
• issues[] — each { wcag_ref, severity, ref, description, fix_suggestion, target }.
• report_path — path to the JSON or markdown report.

Process

1. Build audit_a11y input from the user's intent:
   • open: { platform: 'web', url: <target> }
   • level, report_format.
2. Call the tool.
3. Surface counts + critical/serious issues inline; reference the report path for the full list.

Evidence routing

Run artifacts are saved under:

• Standalone: .rolepod-uiproof/artifacts/<prefix>_<ts>_<uuid>/
• With rolepod parent (detected via the marker file <git-root>/.rolepod/parent-active written by the parent's SessionStart hook): <git-root>/.rolepod/evidence/<ts>-rolepod-uiproof-<skill>/

Either way the run directory contains a manifest.json per Extension Protocol v1, so the parent's check-work skill can aggregate results into the verify phase report. Standalone users can read the manifest themselves — same shape.

If the tool is unavailable

Surface plainly:

The /audit-a11y skill needs the rolepod-uiproof MCP server, which is not currently available. Confirm the plugin is installed and try again.

Do not attempt another backend (D-024).

Examples

Audit example.com at WCAG-AA

{
  "open": { "platform": "web", "url": "https://example.com" },
  "level": "wcag-aa",
  "report_format": "json"
}

Returns:

{
  "run_id": "audit_…",
  "counts": { "critical": 0, "serious": 0, "moderate": 0, "minor": 0 },
  "issues": [],
  "report_path": ".rolepod-uiproof/artifacts/audit_…/report.json"
}